leaked prompts of GPTs

DSPy: The framework for programming—not prompting—foundation models

Low latency JSON generation using LLMs ⚡️

MobileVLM: A Fast, Strong and Open Vision Language Assistant for Mobile Devices

An Open-Source Assistants API and GPTs alternative. Dify.AI is an LLM application development platform. It integrates the concepts of Backend as a Service and LLMOps, covering the core tech stack r…

Self-hosted version of OpenAI’s new stateful Assistants API

The official repo of Qwen-VL (通义千问-VL) chat & pretrained large vision language model proposed by Alibaba Cloud.

🌟 The Multi-Agent Framework: Given one line Requirement, return PRD, Design, Tasks, Repo

Custom prompt styler node for SDXL in ComfyUI

A version of BabyAGI with numpy instead of pinecone and an evaluation agent to check success criteria

Locally run an Instruction-Tuned Chat-Style LLM

The simplest way to run LLaMA on your local machine

Implementation of some unbalanced loss like focal_loss, dice_loss, DSC Loss, GHM Loss et.al

Robust Speech Recognition via Large-Scale Weak Supervision

⚡ A fast embedded library for approximate nearest neighbor search

🔮 Build cross-modal and multimodal applications on the cloud · Neural Search · Creative AI · Cloud Native · MLOps

🧬 The data structure for unstructured multimodal data · Neural Search · Vector Search · Document Store

Papers and code of Explainable AI esp. w.r.t. Image classificiation

🔥🔥🔥🔥 YOLO with Transformers and Instance Segmentation, with TensorRT acceleration! 🔥🔥🔥

RWKV v2 is a RNN with transformer-level performance. It can be directly trained like a GPT transformer (parallelizable). So it's combining the best of RNN and transformer - great performance, fast …

You Only Look at One Sequence (NeurIPS 2021)

Top K Frequent Items in a Time-sliding Window

YOLOv5 🚀 in PyTorch > ONNX > CoreML > TFLite

ConvNet learns to play Need For Speed

Triton backend that enables pre-process, post-processing and other logic to be implemented in Python.

An arbitrary style transfer algorithm

Create random images

tensorflow.keras implementation of gradcam and gradcam++

Fast and accurate single-person pose estimation, ranked 10th at CVPR'19 LIP challenge. Contains implementation of "Global Context for Convolutional Pose Machines" paper.

Code for paper: "Visual Explanation for Deep Metric Learning"